從 Context 流失到自我修復 CI：Anthropic 的工程實戰觀察
Anthropic 工程師在臺北 Meetup 分享：如何透過 hooks 與自動化機制，把 CI 的回饋迴路產品化，減少等待與人工重工。
Technical
IT industry technical articles covering AWS, Azure, Java, Python, SQL, DevOps, and more.
From Context Loss to Self-Healing CI: Observations from Anthropic’s Engineering Practice
Anthropic engineers shared at a Taipei Meetup how hooks and automation can productize CI’s feedback loop, reducing waiting and manual rework.
DevOps 沒有取代 SDLC，AI 也不會
PR merge 速度翻倍，rollback 次數也跟著翻倍。AI 加速的是寫程式碼那一段,但 review 與測試的反饋網沒跟著加密。本文拆解 SDLC、DevOps、CI/CD 三層架構,看 AI 該被擺進哪一層。
DevOps Didn’t Replace SDLC. Neither Will AI.
PR merge count doubled — and so did production rollbacks. After adopting AI tools, one team watched weekly merges climb from 32 to 71, while monthly rollbacks jumped from 2 to 5. Every rolled-back PR had passed CI. AI accelerated the coding part, but the feedback net of review and testing didn’t become denser to match. This post breaks down the three-layer architecture of SDLC, DevOps, and CI/CD, and looks at which layer AI should be placed in.
CI Broke Again Over a Lint Error—Can AI Just Fix It?
Most CI failures are lint errors, typos, and formatting issues—anyone can fix them, but each round costs 10 minutes of waiting. Anthropic’s internal YOLO Push concept lets Claude auto-fix these mechanical failures, with a complete GitHub Action YAML example and safety boundary design.
CI 失敗→複製錯誤→手動修→再等 10 分鐘——這個循環可以自動化嗎？
CI 失敗最常見的原因是 lint error、typo、格式問題——任何人都能修，卻要等 10 分鐘。Anthropic 內部的 YOLO Push 概念讓 Claude 自動修復這類機械性失敗，含官方 GitHub Action YAML 範例和安全邊界設計。
Agent 很慢、LLM 不夠聰明——什麼時候該用多步驟處理？
LLM 一次回答不完整，Agent 又跑很久還常卡住——單次呼叫、CoT、RAG、Agent 到底怎麼選？一張光譜圖 + 5 個問題幫你判斷。
Single Call vs Agent: A Spectrum of LLM Strategies
Single LLM calls miss details. Agents take forever and get stuck. What are the options in between? A visual spectrum + 5 questions to help you decide.
AI Outputs ‘用户’ ‘调用’? One Command to Convert to Taiwan Chinese
LLM-generated Chinese often mixes terminology from different regions. Taiwan readers stumble over Mainland terms like ‘用户’ and ‘调用’. The zhtw tool lets you localize with one command—supporting CLI, Python integration, and batch processing.
AI 輸出『用戶』『調用』？一個指令轉成台灣用語
LLM 生成的中文內容常混合不同地區用語，台灣讀者看到『用戶』『調用』會出戲。zhtw 工具讓你一個指令完成在地化，支援 CLI、Python 整合、批次處理。